文章基本信息

标题：Building Recurrent Neural Networks to Implement Multiple Attractor Dynamics Using the Gradient Descent Method
本地全文：下载
作者：Jun Namikawa ; Jun Tani
期刊名称：Advances in Artificial Neural Systems
印刷版ISSN：1687-7594
电子版ISSN：1687-7608
出版年度：2009
卷号：2009
DOI：10.1155/2009/846040
出版社：Hindawi Publishing Corporation
摘要：The present paper proposes a recurrent neural network model and learning algorithm that can acquire the ability to generate desired multiple sequences. The network model is a dynamical system in which the transition function is a contraction mapping, and the learning algorithm is based on the gradient descent method. We show a numerical simulation in which a recurrent neural network obtains a multiple periodic attractor consisting of five Lissajous curves, or a Van der Pol oscillator with twelve different parameters. The present analysis clarifies that the model contains many stable regions as attractors, and multiple time series can be embedded into these regions by using the present learning method.